Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    蓟
    -0.07
    挽
    -0.07
     Doming
    -0.07
    _MIN
    -0.07
     viewType
    -0.07
     magazine
    -0.07
     yüz
    -0.07
    有这样的
    -0.07
    そう
    -0.07
    盲目
    -0.07
    POSITIVE LOGITS
    会
    0.08
    運用
    0.07
    뽄
    0.07
     through
    0.07
     mềm
    0.07
    рус
    0.06
    ยว
    0.06
    増え
    0.06
    浃
    0.06
    בחן
    0.06
    Act Density 0.038%

    No Known Activations